An interactive neural network-based approach for solving multiple criteria decision-making problems

In this paper, a new approach for solving multiple criteria decision-making (MCDM) problems is proposed based on Decision Neural Network (DNN). The DNN is used to capture and represent the Decision Maker's (DM's) preference. Then, with DNN, an optimization problem is solved to search for the most desirable solution. Procedures of model modification through an interactive procedure, and model optimization are also discussed. An example is given to illustrate the approach and the result is compared with the Interactive FFANN Procedure [Manage. Sci. 42 (1996)]. The result shows that the DNN approach is an encouraging and robust method for solving MCDM problems. (C) 2002 Elsevier Science B.V. All rights reserved.